# CARS: Continuous Evolution for Efficient Neural Architecture Search

arXiv: https://arxiv.org/abs/1909.04977 · HTML: https://mlsanity.com/paper/1909.04977/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2019.

## Built on by (most cited first, 30 of 79)

- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [Parameter Prediction for Unseen Deep Architectures](https://mlsanity.com/paper/2110.13100/) (2021)
- [Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition](https://mlsanity.com/paper/2102.01063/) (2021)
- [ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients](https://mlsanity.com/paper/2301.11300/) (2023)
- [Combined Depth Space based Architecture Search For Person Re-identification](https://mlsanity.com/paper/2104.04163/) (2021)
- [Manifold Regularized Dynamic Network Pruning](https://mlsanity.com/paper/2103.05861/) (2021)
- [Scaling Image and Video Generation via Test-Time Evolutionary Search](https://mlsanity.com/paper/2505.17618/) (2025)
- [Stronger NAS with Weaker Predictors](https://mlsanity.com/paper/2102.10490/) (2021)
- [AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search](https://mlsanity.com/paper/2403.19232/) (2024)
- [BN-NAS: Neural Architecture Search with Batch Normalization](https://mlsanity.com/paper/2108.07375/) (2021)
- [Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model](https://mlsanity.com/paper/2105.15089/) (2021)
- [Analyzing and Mitigating Interference in Neural Architecture Search](https://mlsanity.com/paper/2108.12821/) (2021)
- [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022)
- [OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization](https://mlsanity.com/paper/2205.11141/) (2022)
- [Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generator](https://mlsanity.com/paper/2103.07289/) (2021)
- [GhostNets on Heterogeneous Devices via Cheap Operations](https://mlsanity.com/paper/2201.03297/) (2022)
- [EZNAS: Evolving Zero Cost Proxies For Neural Architecture Scoring](https://mlsanity.com/paper/2209.07413/) (2022)
- [BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation](https://mlsanity.com/paper/2106.14033/) (2021)
- [Neural Architecture Dilation for Adversarial Robustness](https://mlsanity.com/paper/2108.06885/) (2021)
- [DropNAS: Grouped Operation Dropout for Differentiable Architecture Search](https://mlsanity.com/paper/2201.11679/) (2022)
- [A Survey on Computationally Efficient Neural Architecture Search](https://mlsanity.com/paper/2206.01520/) (2022)
- [Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks](https://mlsanity.com/paper/2101.06507/) (2021)
- [SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS](https://mlsanity.com/paper/2403.04161/) (2024)
- [Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluation](https://mlsanity.com/paper/2108.04541/) (2021)
- [EEEA-Net: An Early Exit Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2108.06156/) (2021)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search](https://mlsanity.com/paper/2104.04141/) (2021)
- [PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2204.12726/) (2022)

## Abstract (arXiv)

Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for searching neural networks. Architectures in the population that share parameters within one SuperNet in the latest generation will be tuned over the training dataset with a few epochs. The searching in the next evolution generation will directly inherit both the SuperNet and the population, which accelerates the optimal network generation. The non-dominated sorting strategy is further applied to preserve only results on the Pareto front for accurately updating the SuperNet. Several neural networks with different model sizes and performances will be produced after the continuous search with only 0.4 GPU days. As a result, our framework provides a series of networks with the number of parameters ranging from 3.7M to 5.1M under mobile settings. These networks surpass those produced by the state-of-the-art methods on the benchmark ImageNet dataset.